app.py

app.py

@@ -0,0 +1,106 @@
+import cv2
+import mediapipe as mp
+import numpy as np
+import gradio as gr
+import tempfile
+
+# Load model
+MODEL_PATH = "hand_landmarker.task"
+
+BaseOptions = mp.tasks.BaseOptions
+HandLandmarker = mp.tasks.vision.HandLandmarker
+HandLandmarkerOptions = mp.tasks.vision.HandLandmarkerOptions
+VisionRunningMode = mp.tasks.vision.RunningMode
+mp_image = mp.Image
+mp_format = mp.ImageFormat
+
+# Finger connections and colors
+HAND_CONNECTIONS = [
+    (0, 1), (1, 2), (2, 3), (3, 4),
+    (0, 5), (5, 6), (6, 7), (7, 8),
+    (0, 9), (9,10), (10,11), (11,12),
+    (0,13), (13,14), (14,15), (15,16),
+    (0,17), (17,18), (18,19), (19,20)
+]
+
+FINGER_COLORS = {
+    'thumb': (245, 245, 245),
+    'index': (128, 0, 128),
+    'middle': (0, 255, 0),
+    'ring': (0, 165, 255),
+    'pinky': (255, 0, 0),
+    'palm': (100, 100, 100)
+}
+
+def get_finger_color(start_idx):
+    if start_idx in range(0, 5):
+        return FINGER_COLORS['thumb']
+    elif start_idx in range(5, 9):
+        return FINGER_COLORS['index']
+    elif start_idx in range(9, 13):
+        return FINGER_COLORS['middle']
+    elif start_idx in range(13, 17):
+        return FINGER_COLORS['ring']
+    elif start_idx in range(17, 21):
+        return FINGER_COLORS['pinky']
+    else:
+        return FINGER_COLORS['palm']
+
+def process_video(video_path):
+    cap = cv2.VideoCapture(video_path)
+
+    fourcc = cv2.VideoWriter_fourcc(*'mp4v')
+    tmp_out = tempfile.NamedTemporaryFile(suffix=".mp4", delete=False)
+    out_path = tmp_out.name
+
+    fps = cap.get(cv2.CAP_PROP_FPS)
+    w = int(cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+    h = int(cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+    out = cv2.VideoWriter(out_path, fourcc, fps, (w, h))
+
+    options = HandLandmarkerOptions(
+        base_options=BaseOptions(model_asset_path=MODEL_PATH),
+        running_mode=VisionRunningMode.IMAGE,
+        num_hands=2,
+        min_hand_detection_confidence=0.5,
+        min_hand_presence_confidence=0.5,
+        min_tracking_confidence=0.5
+    )
+
+    with HandLandmarker.create_from_options(options) as landmarker:
+        while cap.isOpened():
+            ret, frame = cap.read()
+            if not ret:
+                break
+
+            rgb_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
+            mp_img = mp_image(image_format=mp_format.SRGB, data=rgb_frame)
+            results = landmarker.detect(mp_img)
+
+            if results.hand_landmarks:
+                for hand_landmarks in results.hand_landmarks:
+                    points = [(int(lm.x * w), int(lm.y * h)) for lm in hand_landmarks]
+
+                    for start, end in HAND_CONNECTIONS:
+                        color = get_finger_color(start)
+                        cv2.line(frame, points[start], points[end], color, 2)
+
+                    for i, (x, y) in enumerate(points):
+                        cv2.circle(frame, (x, y), 4, (0, 255, 255), -1)
+
+            out.write(frame)
+
+    cap.release()
+    out.release()
+    return out_path
+
+# Gradio interface
+demo = gr.Interface(
+    fn=process_video,
+    inputs=gr.Video(label="Upload Video or Use Webcam"),
+    outputs=gr.Video(label="Hand Landmark Annotated Video"),
+    title="Hand Detection ",
+    description="Upload a video or use webcam to detect hands."
+)
+
+demo.launch()